A source-free teacher-student domain adaptation framework, trained on weather data from one US state and adapted to another with 20% labeled target data, reportedly improves solar power prediction by up to 11.36% over a non-adaptive baseline.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Semi-Supervised Deep Domain Adaptation for Predicting Solar Power Across Different Locations
A source-free teacher-student domain adaptation framework, trained on weather data from one US state and adapted to another with 20% labeled target data, reportedly improves solar power prediction by up to 11.36% over a non-adaptive baseline.